{"id":19999915,"url":"https://github.com/eliphatfs/skeletonmerger","last_synced_at":"2025-05-04T14:32:45.072Z","repository":{"id":52688254,"uuid":"346933729","full_name":"eliphatfs/SkeletonMerger","owner":"eliphatfs","description":"Code repository for paper `Skeleton Merger: an Unsupervised Aligned Keypoint Detector`.","archived":false,"fork":false,"pushed_at":"2022-11-20T03:24:13.000Z","size":115,"stargazers_count":48,"open_issues_count":1,"forks_count":11,"subscribers_count":2,"default_branch":"main","last_synced_at":"2023-03-01T11:25:15.477Z","etag":null,"topics":["3d-computer-vision","cvpr2021","pytorch","unsupervised-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/eliphatfs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-03-12T04:11:45.000Z","updated_at":"2022-11-14T00:21:29.000Z","dependencies_parsed_at":"2023-01-23T13:46:10.031Z","dependency_job_id":null,"html_url":"https://github.com/eliphatfs/SkeletonMerger","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2FSkeletonMerger","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2FSkeletonMerger/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2FSkeletonMerger/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2FSkeletonMerger/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eliphatfs","download_url":"https://codeload.github.com/eliphatfs/SkeletonMerger/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224393836,"owners_count":17303725,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["3d-computer-vision","cvpr2021","pytorch","unsupervised-learning"],"created_at":"2024-11-13T05:13:18.443Z","updated_at":"2024-11-13T05:13:18.971Z","avatar_url":"https://github.com/eliphatfs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Skeleton Merger\nSkeleton Merger, an Unsupervised Aligned Keypoint Detector.\nThe paper is available at [https://arxiv.org/abs/2103.10814](https://arxiv.org/abs/2103.10814).\n\n[\u003cimg src=\"_readme_resources/intropic.jpg\" width=\"50%\" alt=\"Intro pic\" /\u003e](_readme_resources/intropic.jpg)\n\n**Update Aug. 6th:** The point cloud visualizer is now released! See [https://github.com/eliphatfs/PointCloudVisualizer](https://github.com/eliphatfs/PointCloudVisualizer).\n\n## A map of the repository\n+ The `merger/pointnetpp` folder contains the [Pytorch Implementation of PointNet and PointNet++](https://github.com/yanx27/Pointnet_Pointnet2_pytorch) repository with some minor changes. It is adapted to make compatible relative imports.\n+ The `merger/composed_chamfer.py` file contains an efficient implementation of proposed Composite Chamfer Distance (CCD).\n+ The `merger/data_flower.py` file is for data loading and preprocessing.\n+ The `merger/merger_net.py` file contains the `Skeleton Merger` implementation.\n+ The root folder contains several scripts for training and testing.\n\nYou can find a pre-trained model on chairs from ShapeNetCore [here](https://github.com/eliphatfs/SkeletonMerger/issues/8). Notice that axis order (e.g., gravity axis may be either y or z) and scaling may vary between datasets, so it is recommended to train a model locally from scratch if you need to use Skeleton Merger. It's fast! Skeleton Merger usually gives reasonable results within 5-10 epochs, which only takes minutes on ShapeNetCore-scale datasets with a GTX 1080. (For full power of the model you still need to train for 50-100 epochs and do some epoch selection by validation error or by the downstream task.)\n\n## Usage of script files\nUsage of the script files, together with a brief description of data format, are available through the `-h` command line option.\n\n## Dataset\nThe ShapeNetCore.v2 dataset used in the paper is available from the [Point Cloud Datasets](https://github.com/AnTao97/PointCloudDatasets) repository.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feliphatfs%2Fskeletonmerger","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feliphatfs%2Fskeletonmerger","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feliphatfs%2Fskeletonmerger/lists"}